Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2297 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0481. Min Range: -7.0481
Max Act: 7.0481. Min Act: -0.1700
Data Index: 5113303 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0481. Min Range: -7.0481
Max Act: 7.0168. Min Act: -0.1700
Data Index: 6731932 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0481. Min Range: -7.0481
Max Act: 7.0168. Min Act: -0.1700
Data Index: 4672411 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.8606. Min Act: -0.1700
Data Index: 6957813 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.8606. Min Act: -0.1700
Data Index: 3548327 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.8293. Min Act: -0.1700
Data Index: 7898518 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.7668. Min Act: -0.1700
Data Index: 4999556 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.7668. Min Act: -0.1700
Data Index: 4437535 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.7043. Min Act: -0.1700
Data Index: 1236876 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.7356. Min Act: -0.1700
Data Index: 12797 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.6731. Min Act: -0.1700
Data Index: 6445614 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.6106. Min Act: -0.1700
Data Index: 7318671 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.6106. Min Act: -0.1700
Data Index: 6841801 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.5793. Min Act: -0.1700
Data Index: 6056099 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.5481. Min Act: -0.1700
Data Index: 5259187 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.5481. Min Act: -0.1700
Data Index: 6925289 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.5481. Min Act: -0.1700
Data Index: 6665974 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8823217 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8807797 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0481. Min Range: -7.0481
Max Act: 6.4856. Min Act: -0.1700
Data Index: 3444523 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19